Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing
CVE-2026-61539 · GHSA-x2rj-828p-hx9m · published 2026-08-21 · updated 2026-10-08
- Severity
- Critical
- CVSS score
- 10.0
- Chance of exploitation (EPSS)
- 1.2%
- Fixed in
- 2.7.0
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Total
- CISA SSVC
Xinference used Python's unsafe eval() function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to return a Python expression. Xinference then evaluates that expression on the server while post-processing the tool-call result. In the tested default deployment, authentication was not enabled, so the vulnerability was exploitable by an unauthenticated remote attacker through the /v1/chat/completions endpoint.
Upgrade xinference to 2.7.0 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| xinference | PyPI | <= 2.5.0 | 2.7.0 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalMalicious code in xinference (PyPI)xinference, xinference, xinference
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.